skillopt-sleep

Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into a Cursor skill, or requests SkillOpt-Sleep status, harvest, dry-run, run, scheduling, review, or adoption. Drives the validation-gated skillopt_sleep engine with Cursor transcripts and the optional Cursor Agent CLI backend.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and workflow-clear, with executable commands and validation-gated feedback loops throughout. The main gap is conciseness/structure: dense flag and backend enumerations could be split into reference files or tightened.

Suggestions

Move the backend list and the per-flag reference into a separate references file (e.g. references/commands.md) and link to it from SKILL.md to improve progressive_disclosure and conciseness.

Consolidate the repeated TARGET_SKILL= assignment into one place and reference it, trimming redundant token use.

Tighten the flag enumeration block by grouping related flags into a short table rather than a long bulleted list.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense and assumes competence (no concept-padding), but the long flag-by-flag enumeration and repeated TARGET_SKILL assignments could be trimmed, matching the 'efficient; minor instances that could be trimmed' anchor.	4 / 5
Actionability	Provides copy-paste-ready skillopt-sleep command blocks with exact flags, a concrete config JSON snippet, and explicit file paths, covering status/harvest/dry-run/run/adopt; meets the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	A clear 7-step Core workflow with a validation gate and explicit feedback checkpoints ('Inspect counts before the first real run', 'Only then run', 'Offer adoption only after the user reviews') matches the anchor for a clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	Sections are well-organized and self-contained with no broken references, but at ~220 lines with dense backend/flag enumerations it stays in a single file rather than splitting detail into reference files, so it does not reach the 'clear overview with one-level-deep references' anchor.	4 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it pairs a concrete what-statement with an explicit, multi-condition 'Use when...' trigger clause and is clearly niche-scoped. Minor room to convert command-name enumerations into more natural user phrasings.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (harvest, dry-run, run, scheduling, review, adoption) and names a concrete engine, matching the 'several specific actions; minor gaps' anchor; not 5 because several actions are command-name enumerations rather than richly distinct capabilities.	4 / 5
Completeness	An explicit 'Use when...' clause enumerates concrete triggers and a separate sentence states what the skill does ('Drives the validation-gated skillopt_sleep engine...'), satisfying the anchor for clearly and explicitly answering both what and when.	5 / 5
Trigger Term Quality	Includes natural phrasings ('wants Cursor to learn from recent local sessions', 'offline sleep or dream cycle') plus command-verb triggers; good coverage but some triggers lean on technical command names a user would not naturally say, so it sits below 5.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to 'SkillOpt-Sleep', Cursor transcripts, and an offline dream cycle, giving it a clear niche with minimal overlap risk versus other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/SkillOpt
Path: plugins/cursor/skills/skillopt-sleep/SKILL.md
Commit: bdfdc30

Reviewed: about 2 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.